NVIDIA Releases Cosmos3-Nano Robotics Fine-Tune Targeting VLA and LIBERO Tasks on Hugging Face
nvidia · hf · 2026-10-19
NVIDIA uploaded cosmos3-nano-libero10-sdg-export-S2s43 to Hugging Face — a robotics fine-tune of its Cosmos3-Nano base model, tagged for VLA (vision-language-action) work and related to the LIBERO benchmark.
Weights ship as safetensors with customcode loading and a non-standard 'other' license. A routine but useful asset update for those following embodied model training pipelines and synthetic data generation.
More from Embodied
- MIT CSAIL's X-Hinges 3D-Prints Everyday Objects With Built-In Sensing Across Three Motion Axes — MIT News AI · 2026-10-23
- Formic raises $50M Series B to scale physical AI across 100+ US factories — garrytan · 2026-10-23
- fal starts fine-tuning a physical robot to draw, results next week — OdinLovis · 2026-10-23
- PEARL demo: an LLM agent that checks experiment results, revises plans, and re-tests — KevinKaichuang · 2026-10-23
- CU Boulder's ATLAS Institute Opens Tenure-Track Robotics Professorship — ryosuzk · 2026-10-23
- MiTaS multi-resolution tactile imitation learning hits 80% success vs 35.5% vision-only baseline — Jan_R_Peters · 2026-10-23